scdataloader 2.0.12__tar.gz → 2.1.0__tar.gz

{scdataloader-2.0.12 → scdataloader-2.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: scdataloader
-Version: 2.0.12
+Version: 2.1.0
 Summary: a dataloader for single cell data in lamindb
 Project-URL: repository, https://github.com/jkobject/scDataLoader
 Author-email: jkobject <jkobject@gmail.com>
@@ -14,7 +14,7 @@ Requires-Dist: cellxgene-census>=0.1.0
 Requires-Dist: django>=4.0.0
 Requires-Dist: ipykernel>=6.20.0
 Requires-Dist: jupytext>=1.16.0
-Requires-Dist: lamindb[gcp]==2.0.1
+Requires-Dist: lamindb[gcp]==2.1.1
 Requires-Dist: leidenalg>=0.8.0
 Requires-Dist: lightning>=2.3.0
 Requires-Dist: matplotlib>=3.5.0

{scdataloader-2.0.12 → scdataloader-2.1.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "scdataloader"
-version = "2.0.12"
+version = "2.1.0"
 description = "a dataloader for single cell data in lamindb"
 authors = [
     {name = "jkobject", email = "jkobject@gmail.com"}
@@ -11,7 +11,7 @@ requires-python = ">=3.10,<3.13"
 keywords = ["scRNAseq", "dataloader", "pytorch", "lamindb", "scPRINT"]
 dependencies = [
     "numpy<=2.2.0",
-    "lamindb[gcp]==2.0.1",
+    "lamindb[gcp]==2.1.1",
     "cellxgene-census>=0.1.0",
     "torch>=2.2.0",
     "pytorch-lightning>=2.3.0",

{scdataloader-2.0.12 → scdataloader-2.1.0}/scdataloader/preprocess.py

@@ -264,8 +264,9 @@ class Preprocessor:
         # For genes that are already ENS IDs, use them directly
         prev_size = adata.shape[1]
         # Handle symbol genes
+        cols_to_use = adata.var.columns.difference(genesdf.columns)
         if self.is_symbol:
-            new_var = adata.var.merge(
+            new_var = adata.var[cols_to_use].merge(
                 genesdf.drop_duplicates("symbol").set_index("symbol", drop=False),
                 left_index=True,
                 right_index=True,
@@ -275,7 +276,7 @@ class Preprocessor:
             adata = adata[:, new_var.index]
             new_var.index = new_var["ensembl_gene_id"]
         else:
-            new_var = adata.var.merge(
+            new_var = adata.var[cols_to_use].merge(
                 genesdf, left_index=True, right_index=True, how="inner"
             )
             adata = adata[:, new_var.index]

{scdataloader-2.0.12 → scdataloader-2.1.0}/scdataloader/utils.py

@@ -440,6 +440,7 @@ def load_genes(
         "ncbi_gene_ids",
         "synonyms",
         "description",
+        "abbr",
     ]:
         if col in organismdf.columns:
             organismdf.drop(columns=[col], inplace=True)